First commit
Browse files- .gitattributes +1 -0
- added_tokens.json +3 -0
- config.json +72 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 250101
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/mdeberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"finetuning_task": "pos",
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "ADJ",
|
13 |
+
"1": "ADP",
|
14 |
+
"2": "ADV",
|
15 |
+
"3": "AUX",
|
16 |
+
"4": "CCONJ",
|
17 |
+
"5": "DET",
|
18 |
+
"6": "INTJ",
|
19 |
+
"7": "NOUN",
|
20 |
+
"8": "NUM",
|
21 |
+
"9": "PRON",
|
22 |
+
"10": "PROPN",
|
23 |
+
"11": "PUNCT",
|
24 |
+
"12": "SCONJ",
|
25 |
+
"13": "SYM",
|
26 |
+
"14": "VERB",
|
27 |
+
"15": "X"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"ADJ": 0,
|
33 |
+
"ADP": 1,
|
34 |
+
"ADV": 2,
|
35 |
+
"AUX": 3,
|
36 |
+
"CCONJ": 4,
|
37 |
+
"DET": 5,
|
38 |
+
"INTJ": 6,
|
39 |
+
"NOUN": 7,
|
40 |
+
"NUM": 8,
|
41 |
+
"PRON": 9,
|
42 |
+
"PROPN": 10,
|
43 |
+
"PUNCT": 11,
|
44 |
+
"SCONJ": 12,
|
45 |
+
"SYM": 13,
|
46 |
+
"VERB": 14,
|
47 |
+
"X": 15
|
48 |
+
},
|
49 |
+
"layer_norm_eps": 1e-07,
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"max_relative_positions": -1,
|
52 |
+
"model_type": "deberta-v2",
|
53 |
+
"norm_rel_ebd": "layer_norm",
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_hidden_layers": 12,
|
56 |
+
"pad_token_id": 0,
|
57 |
+
"pooler_dropout": 0,
|
58 |
+
"pooler_hidden_act": "gelu",
|
59 |
+
"pooler_hidden_size": 768,
|
60 |
+
"pos_att_type": [
|
61 |
+
"p2c",
|
62 |
+
"c2p"
|
63 |
+
],
|
64 |
+
"position_biased_input": false,
|
65 |
+
"position_buckets": 256,
|
66 |
+
"relative_attention": true,
|
67 |
+
"share_att_key": true,
|
68 |
+
"torch_dtype": "float32",
|
69 |
+
"transformers_version": "4.23.1",
|
70 |
+
"type_vocab_size": 0,
|
71 |
+
"vocab_size": 251000
|
72 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f7e8f16bf54ba0cd7e63a61e62fe14475c1a5b43cbe41fe33490458200f1fd3
|
3 |
+
size 1112995823
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
3 |
+
size 4305025
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f06fc3bbcbbc8f07be861b9a6a69e177247bc549b2bcbf0483e4dd98c06b6f6
|
3 |
+
size 16331301
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"name_or_path": "microsoft/mdeberta-v3-base",
|
8 |
+
"pad_token": "[PAD]",
|
9 |
+
"sep_token": "[SEP]",
|
10 |
+
"sp_model_kwargs": {},
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"split_by_punct": false,
|
13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
14 |
+
"unk_token": "[UNK]",
|
15 |
+
"vocab_type": "spm"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:045b63cdede68056d072e04ef17039f71e58e32ef8be693de385c2cad929c634
|
3 |
+
size 3375
|